{ "best_metric": 0.528473834809328, "best_model_checkpoint": "training_dir-augmented\\checkpoint-46510", "epoch": 5.0, "eval_steps": 500, "global_step": 46510, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.0, "grad_norm": 0.9803293943405151, "learning_rate": 8.086937622256031e-06, "loss": 0.5312, "step": 9302 }, { "epoch": 1.0, "eval_accuracy": 0.40428321678321677, "eval_f1": 0.3406020494510067, "eval_loss": 3.0353851318359375, "eval_precision": 0.6901256632128517, "eval_recall": 0.40428321678321677, "eval_runtime": 16.0409, "eval_samples_per_second": 142.636, "eval_steps_per_second": 17.829, "step": 9302 }, { "epoch": 2.0, "grad_norm": 196.54563903808594, "learning_rate": 6.065203216692024e-06, "loss": 0.3949, "step": 18604 }, { "epoch": 2.0, "eval_accuracy": 0.527972027972028, "eval_f1": 0.526961176646401, "eval_loss": 2.4327211380004883, "eval_precision": 0.6358079986576912, "eval_recall": 0.527972027972028, "eval_runtime": 16.8165, "eval_samples_per_second": 136.057, "eval_steps_per_second": 17.007, "step": 18604 }, { "epoch": 3.0, "grad_norm": 0.016049087047576904, "learning_rate": 4.0434688111280154e-06, "loss": 0.3459, "step": 27906 }, { "epoch": 3.0, "eval_accuracy": 0.4943181818181818, "eval_f1": 0.46533481595237636, "eval_loss": 3.3212876319885254, "eval_precision": 0.6366932825610363, "eval_recall": 0.4943181818181818, "eval_runtime": 16.4685, "eval_samples_per_second": 138.932, "eval_steps_per_second": 17.366, "step": 27906 }, { "epoch": 4.0, "grad_norm": 0.18690501153469086, "learning_rate": 2.0217344055640077e-06, "loss": 0.2889, "step": 37208 }, { "epoch": 4.0, "eval_accuracy": 0.5380244755244755, "eval_f1": 0.5246359275298862, "eval_loss": 2.901275157928467, "eval_precision": 0.606438596036477, "eval_recall": 0.5380244755244755, "eval_runtime": 16.3842, "eval_samples_per_second": 139.647, "eval_steps_per_second": 17.456, "step": 37208 }, { "epoch": 5.0, "grad_norm": 0.032341405749320984, "learning_rate": 0.0, "loss": 0.2405, "step": 46510 }, { "epoch": 5.0, "eval_accuracy": 0.5354020979020979, "eval_f1": 0.528473834809328, "eval_loss": 3.196098566055298, "eval_precision": 0.6116035335408587, "eval_recall": 0.5354020979020979, "eval_runtime": 18.2453, "eval_samples_per_second": 125.402, "eval_steps_per_second": 15.675, "step": 46510 } ], "logging_steps": 500, "max_steps": 46510, "num_input_tokens_seen": 0, "num_train_epochs": 5, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 9.524204110411717e+16, "train_batch_size": 8, "trial_name": null, "trial_params": null }